Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    process

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     speech
    -0.06
    -heading
    -0.06
    ivot
    -0.06
    VB
    -0.06
     alongside
    -0.06
    ΙΚ
    -0.06
    сяг
    -0.06
     shines
    -0.06
    _EXTENSIONS
    -0.06
     Premiership
    -0.06
    POSITIVE LOGITS
     dop
    0.07
    обра�
    0.07
     proces
    0.06
     hip
    0.06
     fraction
    0.06
     Ethan
    0.06
    bage
    0.06
    $__
    0.06
     dakika
    0.06
    allo
    0.06
    Act Density 0.009%

    No Known Activations